Sandbox vectors

Let’s define some vectors which can be used for demonstrations:

manyNumbers <- sample( 1:1000, 20 )
manyNumbers
 [1] 654 486 930  88 523 358 244 940 670 488 986 992 603 765  77 595 894 320 191   8
manyNumbersWithNA <- sample( c( NA, NA, NA, manyNumbers ) )
manyNumbersWithNA
 [1]  NA 603 654  NA 523  NA 986   8 191 320 894 486 670 358 244 930 765 595  77  88 940 488 992
duplicatedNumbers <- sample( 1:5, 10, replace = TRUE )
duplicatedNumbers
 [1] 1 2 2 2 1 4 4 4 3 4
letters
 [1] "a" "b" "c" "d" "e" "f" "g" "h" "i" "j" "k" "l" "m" "n" "o" "p" "q" "r" "s" "t" "u" "v" "w" "x" "y" "z"
LETTERS
 [1] "A" "B" "C" "D" "E" "F" "G" "H" "I" "J" "K" "L" "M" "N" "O" "P" "Q" "R" "S" "T" "U" "V" "W" "X" "Y" "Z"
mixedLetters <- c( sample( letters, 5 ), sample( LETTERS, 5 ) )
mixedLetters
 [1] "p" "l" "w" "f" "z" "T" "B" "L" "G" "J"

Are all/any elements TRUE

all( manyNumbers <= 1000 )
[1] TRUE
all( manyNumbers <= 500 )
[1] FALSE
any( manyNumbers > 1000 )
[1] FALSE
any( manyNumbers > 500 )
[1] TRUE
all( !is.na( manyNumbers ) )
[1] TRUE
any( is.na( manyNumbers ) )
[1] FALSE

Which elements are TRUE

Input: logical vector Output: vector of numbers (positions)

which( manyNumbers > 900 )
[1]  3  8 11 12
which( manyNumbersWithNA > 900 )
[1]  7 16 21 23
which( is.na( manyNumbersWithNA ) )
[1] 1 4 6

Filtering vector elements

manyNumbers[ manyNumbers > 900 ] # indexing by logical vector
[1] 930 940 986 992
manyNumbers[ which( manyNumbers > 900 ) ] # indexing by positions
[1] 930 940 986 992
somePositions <- which( manyNumbers > 900 )
manyNumbers[ somePositions ]
[1] 930 940 986 992

Are some elements among other elements

"A" %in% LETTERS
[1] TRUE
c( "X", "Y", "Z" ) %in% LETTERS
[1] TRUE TRUE TRUE
all( c( "X", "Y", "Z" ) %in% LETTERS )
[1] TRUE
all( mixedLetters %in% LETTERS )
[1] FALSE
any( mixedLetters %in% LETTERS )
[1] TRUE
mixedLetters[ mixedLetters %in% LETTERS ]
[1] "T" "B" "L" "G" "J"
mixedLetters[ !( mixedLetters %in% LETTERS ) ]
[1] "p" "l" "w" "f" "z"
manyNumbers %in% 300:600
 [1] FALSE  TRUE FALSE FALSE  TRUE  TRUE FALSE FALSE FALSE  TRUE FALSE FALSE FALSE FALSE FALSE  TRUE FALSE  TRUE FALSE
[20] FALSE
which( manyNumbers %in% 300:600 )
[1]  2  5  6 10 16 18
sum( manyNumbers %in% 300:600 )
[1] 6

Pick one of two (three) depending on condition

if_else( manyNumbersWithNA >= 500, "large", "small" )
 [1] NA      "large" "large" NA      "large" NA      "large" "small" "small" "small" "large" "small" "large" "small"
[15] "small" "large" "large" "large" "small" "small" "large" "small" "large"
if_else( manyNumbersWithNA >= 500, "large", "small", "UNKNOWN" )
 [1] "UNKNOWN" "large"   "large"   "UNKNOWN" "large"   "UNKNOWN" "large"   "small"   "small"   "small"   "large"  
[12] "small"   "large"   "small"   "small"   "large"   "large"   "large"   "small"   "small"   "large"   "small"  
[23] "large"  
# here integer 0L is needed instead of real 0.0 
# manyNumbersWithNA contains integer numbers and the method complains
if_else( manyNumbersWithNA >= 500, manyNumbersWithNA, 0L ) 
 [1]  NA 603 654  NA 523  NA 986   0   0   0 894   0 670   0   0 930 765 595   0   0 940   0 992

Duplicates and unique elements

unique( duplicatedNumbers )
[1] 1 2 4 3
unique( c( NA, duplicatedNumbers, NA ) )
[1] NA  1  2  4  3
duplicated( duplicatedNumbers )
 [1] FALSE FALSE  TRUE  TRUE  TRUE FALSE  TRUE  TRUE FALSE  TRUE

Positions of max/min elements

which.max( manyNumbersWithNA )
[1] 23
manyNumbersWithNA[ which.max( manyNumbersWithNA ) ]
[1] 992
which.min( manyNumbersWithNA )
[1] 8
manyNumbersWithNA[ which.min( manyNumbersWithNA ) ]
[1] 8
range( manyNumbersWithNA, na.rm = TRUE )
[1]   8 992

Sorting/ordering of vectors

manyNumbersWithNA
 [1]  NA 603 654  NA 523  NA 986   8 191 320 894 486 670 358 244 930 765 595  77  88 940 488 992
sort( manyNumbersWithNA )
 [1]   8  77  88 191 244 320 358 486 488 523 595 603 654 670 765 894 930 940 986 992
sort( manyNumbersWithNA, na.last = TRUE )
 [1]   8  77  88 191 244 320 358 486 488 523 595 603 654 670 765 894 930 940 986 992  NA  NA  NA
sort( manyNumbersWithNA, na.last = TRUE, decreasing = TRUE )
 [1] 992 986 940 930 894 765 670 654 603 595 523 488 486 358 320 244 191  88  77   8  NA  NA  NA
manyNumbersWithNA[1:5]
[1]  NA 603 654  NA 523
order( manyNumbersWithNA[1:5] )
[1] 5 2 3 1 4
rank( manyNumbersWithNA[1:5] )
[1] 4 2 3 5 1
sort( mixedLetters )
 [1] "B" "f" "G" "J" "l" "L" "p" "T" "w" "z"

Ranking of vectors

manyDuplicates <- sample( 10:15, 10, replace = TRUE )
rank( manyDuplicates )
 [1] 4.5 7.5 1.0 4.5 9.5 7.5 2.5 9.5 6.0 2.5
rank( manyDuplicates, ties.method = "min" )
 [1] 4 7 1 4 9 7 2 9 6 2
rank( manyDuplicates, ties.method = "random" )
 [1]  4  8  1  5 10  7  2  9  6  3

Rounding numbers

v <- c( -1, -0.5, 0, 0.5, 1, rnorm( 10 ) )
v
 [1] -1.000000000 -0.500000000  0.000000000  0.500000000  1.000000000  0.945914121  0.327396655 -0.274985578  2.083608263
[10] -0.003328552  1.354009215 -0.578535094  0.027743352  0.227650207  0.265220505
round( v, 0 )
 [1] -1  0  0  0  1  1  0  0  2  0  1 -1  0  0  0
round( v, 1 )
 [1] -1.0 -0.5  0.0  0.5  1.0  0.9  0.3 -0.3  2.1  0.0  1.4 -0.6  0.0  0.2  0.3
round( v, 2 )
 [1] -1.00 -0.50  0.00  0.50  1.00  0.95  0.33 -0.27  2.08  0.00  1.35 -0.58  0.03  0.23  0.27
floor( v )
 [1] -1 -1  0  0  1  0  0 -1  2 -1  1 -1  0  0  0
ceiling( v )
 [1] -1  0  0  1  1  1  1  0  3  0  2  0  1  1  1

Naming vector elements

heights <- c( Amy = 166, Eve = 170, Bob = 177 )
heights
Amy Eve Bob 
166 170 177 
names( heights )
[1] "Amy" "Eve" "Bob"
names( heights ) <- c( "AMY", "EVE", "BOB" )
heights
AMY EVE BOB 
166 170 177 
heights[[ "EVE" ]]
[1] 170

Generating grids

expand_grid( x = c( 1:3, NA ), y = c( "a", "b" ) )
# A tibble: 8 x 2
      x y    
  <int> <chr>
1     1 a    
2     1 b    
3     2 a    
4     2 b    
5     3 a    
6     3 b    
7    NA a    
8    NA b    

Generating combinations

combn( c( "a", "b", "c", "d", "e" ), m = 2, simplify = TRUE )
     [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
[1,] "a"  "a"  "a"  "a"  "b"  "b"  "b"  "c"  "c"  "d"  
[2,] "b"  "c"  "d"  "e"  "c"  "d"  "e"  "d"  "e"  "e"  
combn( c( "a", "b", "c", "d", "e" ), m = 3, simplify = TRUE )
     [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
[1,] "a"  "a"  "a"  "a"  "a"  "a"  "b"  "b"  "b"  "c"  
[2,] "b"  "b"  "b"  "c"  "c"  "d"  "c"  "c"  "d"  "d"  
[3,] "c"  "d"  "e"  "d"  "e"  "e"  "d"  "e"  "e"  "e"  


Copyright © 2021 Biomedical Data Sciences (BDS) | LUMC